agentmods.dev

deeplaw-compile-source

deeplaw-compile-source is a skill for Claude Code, Codex from Eysn0130/DeepLaw. It costs 46 tokens per session (329 once invoked), scanned A, original, Apache-2.0.

An instruction set for turning an approved DeepLaw source revision into governed knowledge objects or Living Wiki entries.

In plain words
What is it for?
It is for compiling selected source material into DeepLaw's knowledge system through its controlled compilation steps.
Why use it?
It enforces owner permission, source checks, provenance, and validation throughout the compilation process.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the deeplaw-knowledge-os plugin — 8 skills, 5 hooks shipped together

not rated 6repo 1mo ago A scan 46 tokens original Apache-2.0

Good fit It is for compiling selected source material into DeepLaw's knowledge system through its controlled compilation steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eysn0130/deeplaw/deeplaw-compile-source
View source ↗ Eysn0130/DeepLaw
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Eysn0130/DeepLaw --skill deeplaw-compile-source
Clone the repo
git clone --depth 1 https://github.com/Eysn0130/DeepLaw

Made for: Claude Code, Codex.

Or install deeplaw-knowledge-os, the plugin that ships this one along with the rest of its 8 skills, 5 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deeplaw-compile-source

README.md
[![agentmods](https://agentmods.dev/badge/skills/eysn0130/deeplaw/deeplaw-compile-source/github.svg)](https://agentmods.dev/skills/eysn0130/deeplaw/deeplaw-compile-source)
Your own site
<a href="https://agentmods.dev/skills/eysn0130/deeplaw/deeplaw-compile-source"><img src="https://agentmods.dev/badge/skills/eysn0130/deeplaw/deeplaw-compile-source/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deeplaw-compile-source

Your own site · 80×15
<a href="https://agentmods.dev/skills/eysn0130/deeplaw/deeplaw-compile-source"><img src="https://agentmods.dev/badge/skills/eysn0130/deeplaw/deeplaw-compile-source.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00329
Opus 5.5 $0.00018 $0.00132
Sonnet 5.5 $0.00009 $0.00066
Haiku 4.5 $0.00005 $0.00033

Measured 2mo ago against content hash e0a3f2ee4557, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deeplaw-compile-source scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/deeplaw-knowledge-os/skills/deeplaw-compile-source/SKILL.md · 24 lines

What it actually says

Compile an Admitted Source

Require a user-selected Source Revision and confirm_no_case_data=true.

  1. Ask the owner to obtain the read-only handoff with deeplaw knowledge compile handoff --source-revision-id <exact-id>. Verify that it names knowledge_support and knowledge_sink, includes no grant, performed no write, and reports the exact Source status. Then read with knowledge_support: use operation=source to identify the exact revision and operation=compilation with compilation_action=list_uncompiled or profile.
  2. Require a separately owner-created, scope-bound Grant for knowledge_sink. Never create, widen, inspect, or copy a Grant.
  3. Use the explicit sink lifecycle: begin_compilation, stage_semantic_observations, freeze_semantic_inventory, finalize_semantic_compilation, validate_compilation, commit_compilation, then resume_compilation with projection requested. Supply fresh idempotency keys.
  4. Let DeepLaw validate identity, source binding, provenance, lifecycle, and authority. Never write Markdown or databases directly, invoke a model automatically, or promote a draft.
  5. Verify the committed revision and report partial status, gaps, conflicts, and projection state.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 24 lines · 46 tokens per session scan A e0a3f2ee4557

Subscribe to this mod's changes

deeplaw-compile-source is a skill published in the GitHub repository Eysn0130/DeepLaw (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 329 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeLegal and compliancechinese-lawcodexlegal-researchmcpopencode
Related

deeplaw-compile-source compared with skills from other repositories

deeplaw-compile-source next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deeplaw-compile-sourceEysn0130/DeepLawSkill61mo agoApache-2.0A46Claude Code, Codex
contract-guardianlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA245Claude Code, Codex
法律周报lawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA242Claude Code, Codex
legal-researchlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA87Claude Code, Codex
legal-citation-comprehensivelawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA119Claude Code, Codex
legal-fact-checkerlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA143Claude Code, Codex
workflow-overviewlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA63Claude Code, Codex